CAREER: Optimism in Causal Reasoning via Information-theoretic Methods

职业：通过信息论方法进行因果推理的乐观主义

基本信息

批准号：
2239375
负责人：
Murat Kocaoglu
金额：
$ 60万
依托单位：
Purdue University
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2023
资助国家：
美国
起止时间：
2023-01-15 至 2027-12-31
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2239375&HistoricalAwards=false
关键词：
CAREER Optimism Causal Reasoning via

项目摘要

Reasoning about the causes and effects of phenomena is a fundamental problem in the development of artificial intelligence. Causal reasoning from data also plays a key role in several disciplines, from engineering and computer science to medical research. A formal mathematical theory of probabilistic causation has been developed in the last few decades by Pearl (1995). Several algorithms that illustrate how much qualitative and quantitative causal knowledge can be extracted from data under well-defined assumptions have been proposed within this formalism. These algorithms employ a worst-case view: if the answer to a causal question is not unique, they return that the result is not identifiable. However, such an approach is unsuitable for many real-world systems that violate these crucial assumptions to varying degrees. The investigator argues that it is possible to significantly expand the applicability of causality theory by identifying simple causal explanations in the data that are unlikely to occur by chance. This project will extend the theory of causation to a much wider set of real-world instances by enabling causal reasoning for most models rather than in the worst case.To expand the scope of the state-of-the-art causal reasoning formalism, the investigator will develop novel algorithms that identify information-theoretically simple explanations of the underlying causal system from data. The first thrust seeks to develop methods to learn causal relations from observational data via an information-theoretic interpretation of Occam’s razor based on the entropy of the causal system. A second thrust will analyze how information-theoretically simple explanations can help approximately compute causal effects that are not identifiable in the worst case. A third thrust will leverage the results of the first two thrusts to develop experimental design algorithms for efficiently learning causal structures and causal effects via interventions.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

关于现象的原因和影响的推理是人工智能发展的基本问题。从工程和计算机科学到医学研究，来自数据的因果推理在几个学科中也起着关键作用。 Pearl（1995）在过去的几十年中已经开发了一种概率原因的形式数学理论。在这种格式化中提出了几种算法，这些算法说明了在定义明确的假设下可以从数据中提取多少定性和定量因果知识。这些算法员工是最糟糕的观点：如果对灾难性问题的答案不是唯一的，那么他们返回结果是无法识别的。但是，这种方法不适合许多在不同程度上违反这些关键假设的现实世界系统。研究者认为，可以通过确定数据中不太可能偶然发生的简单灾难性解释来显着扩大休闲理论的适用性。该项目将通过为大多数模型而不是最坏的情况启用偶然的推理来扩展原因理论，以扩大最先进的因果关系形式的范围，将其扩展到更广泛的现实世界实例，研究人员将开发出新的算法，从而识别来自数据的基本CAUSAL系统的简单解释的新型算法。第一个推力试图通过基于因果系统的熵对Occam的剃须刀的信息理论解释从观察数据中学习因果关系的方法。第二个推力将分析信息理论的简单解释如何有助于大致计算最坏情况下无法识别的灾难效应。第三个推力将利用前两个推力的结果来开发实验设计算法，以通过干预措施有效地学习因果结构和因果关系。该奖项反映了NSF的法定任务，并通过使用基金会的知识分子优点和更广泛的影响审查标准来通过评估来诚实地通过评估来诚实地支持。

项目成果

期刊论文数量（7）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders

具有未观察到的混杂因素的结构性因果强盗的近似分配匹配

DOI：
发表时间：
2023
期刊：
37th Conference on Neural Information Processing Systems (NeurIPS 2023
影响因子：
0
作者：
Wei, L;Elahi, M Q;Ghasemi, M;Kocaoglu, M.
通讯作者：
Kocaoglu, M.

Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier

DOI：
10.48550/arxiv.2302.11838
发表时间：
2023-02
期刊：
影响因子：
0
作者：
Spencer Compton;Dmitriy A. Katz;Benjamin Qi;K. Greenewald;Murat Kocaoglu
通讯作者：
Spencer Compton;Dmitriy A. Katz;Benjamin Qi;K. Greenewald;Murat Kocaoglu

Finding Invariant Predictors Efficiently via Causal Structure

通过因果结构有效找到不变预测变量

DOI：
发表时间：
2023
期刊：
Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023
影响因子：
0
作者：
Lee, K;Rahman, Md M;Kocaoglu, M.
通讯作者：
Kocaoglu, M.

Causal Discovery in Semi-Stationary Time Series

半平稳时间序列中的因果发现

DOI：
发表时间：
2023
期刊：
37th Conference on Neural Information Processing Systems (NeurIPS 2023
影响因子：
0
作者：
Gao, S;Addanki, R;Rossi, Ryan A;Kocaoglu, M.
通讯作者：
Kocaoglu, M.

Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge

DOI：
10.48550/arxiv.2306.11008
发表时间：
2023-06
期刊：
ArXiv
影响因子：
0
作者：
Abhin Shah;Karthikeyan Shanmugam;Murat Kocaoglu
通讯作者：
Abhin Shah;Karthikeyan Shanmugam;Murat Kocaoglu

DOI：
{{ item.doi }}
发表时间：
{{ item.publish_year }}
期刊：
{{ item.journal_name }}
影响因子：
{{ item.factor }}
作者：
{{ item.authors }}
通讯作者：
{{ item.author }}

数据更新时间：{{ journalArticles.updateTime }}

作者：
{{ item.author }}

数据更新时间：{{ monograph.updateTime }}

作者：
{{ item.author }}

数据更新时间：{{ sciAawards.updateTime }}

作者：
{{ item.author }}

数据更新时间：{{ conferencePapers.updateTime }}

作者：
{{ item.author }}

数据更新时间：{{ patent.updateTime }}

Murat Kocaoglu其他文献

Sample Efficient Active Learning of Causal Trees

因果树的高效主动学习示例

DOI：
发表时间：
2019
期刊：
Neural Information Processing Systems
影响因子：
0
作者：
K. Greenewald;Dmitriy A. Katz;Karthikeyan Shanmugam;Sara Magliacane;Murat Kocaoglu;Enric Boix Adserà;Guy Bresler
通讯作者：
Guy Bresler